Teacher since August 2025
Benedict Asante
I explain the kinds of AI models, what they cost to run and how to run one yourself
9
tutors built
4.4Sample
average from 16 reviews
328Sample
lessons taught by their tutors
About Benedict
I teach the practical side of modern models: reasoning models, multimodal models, open and closed weights, running a model on your own computer, and the money, energy and hardware behind every answer. I like starting with something you can see or measure, such as the memory a model needs or the number of tokens a task uses, then explaining the idea behind it. My background is in systems engineering and technical training. I try hard to separate what is known from what is estimated, especially on energy and cost, where confident numbers are often less solid than they look.
Knows about
Tutors by Benedict
9 tutors
Running a language model on your own computer
Work out what your machine can run, set up a local model, and know what to expect from it80 lessonsSampleBenedict Asante$7Reasoning models: when thinking time helpsReasoning models: when thinking time helps
Learn how reasoning models work, when extra thinking pays off, and when it just costs more65 lessonsSampleBenedict Asante$6Open versus closed models, explained fairlyOpen versus closed models, explained fairly
Understand open weights, open source and closed APIs, and how to choose between them62 lessonsSampleBenedict Asante$5AI chips and data centres for non engineersAI chips and data centres for non engineers
Understand the hardware behind AI: why GPUs matter, what data centres do, and why supply is tight59 lessonsSampleBenedict Asante$4Scaling laws and where AI progress comes fromScaling laws and where AI progress comes from
Understand how compute, data and model size drive progress, and the debates about what comes next33 lessonsSampleBenedict Asante$10The energy and water cost of AIThe energy and water cost of AI
Understand what is known and unknown about AI's electricity, water and carbon footprint29 lessonsSampleBenedict Asante$4Multimodal models: text, images and sound togetherMultimodal models: text, images and sound together
See how one model can read images, hear audio and write text, and where it still stumblesBenedict Asante$6Why some models are fast: efficiency tricks insideWhy some models are fast: efficiency tricks inside
Learn the techniques that make models faster and cheaper: from mixture of experts to KV cachingBenedict Asante$11What an AI answer really costsWhat an AI answer really costs
Understand the compute, tokens and money behind AI answers and why prices vary so muchBenedict Asante$5Recent reviews
What students said about Benedict's tutors.
- Ingeborg L.Sample
Finally someone separating estimates from facts. The market based versus location based point helped me read our cloud provider's sustainability report.
- Megan F.Sample
Useful, but my old laptop could only run tiny models and results were weak. The tutor did warn me, to be fair.
- Victoria H.Sample
The kitchen analogy finally made GPU news make sense. The memory bottleneck point was new and very clear.
- Tariq Y.Sample
Finally understood why my model slowed down with long documents: the KV cache. Excellent explanation of quantisation trade offs.
- Stefan J.Sample
The memory arithmetic made everything make sense. I now run a small model locally for client notes that cannot leave my machine.
- Kenneth O.Sample
Balanced. I came in feeling guilty about every prompt and left understanding where the real levers are. Wanted a few more concrete numbers.